相关论文: Subtract the Corruption: Training-Data-Free Correc…

Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowledge originates from…

Unlearning algorithms aim to remove deleted data's influence from trained models at a cost lower than full retraining. However, prior guarantees of unlearning in literature are flawed and don't protect the privacy of deleted records. We…

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained…

Calibration of option pricing models is routinely repeated as markets evolve, yet modern systems lack an operator for removing data from a calibrated model without full retraining. When quotes become stale, corrupted, or subject to deletion…

Deep learning models suffer from catastrophic forgetting when trained in an incremental learning setting. In this work, we propose a novel approach to address the task incremental learning problem, which involves training a model on new…

Machine Unlearning (MUL) is crucial for privacy protection and content regulation, yet recent studies reveal that traces of forgotten information persist in unlearned models, enabling adversaries to resurface removed knowledge. Existing…

A fault-tolerant quantum computation requires an efficient means to detect and correct errors that accumulate in encoded quantum information. In the context of machine learning, neural networks are a promising new approach to quantum error…

Training models on uncurated Text Embeddings (TEs) derived from raw tabular data can lead to a severe failure mode known as model collapse, where predictions converge to a single class regardless of input. By comparing models trained with…

In machine unlearning, $(\varepsilon,\delta)-$unlearning is a popular framework that provides formal guarantees on the effectiveness of the removal of a subset of training data, the forget set, from a trained model. For strongly convex…

Corrupted labels and class imbalance are commonly encountered in practically collected training data, which easily leads to over-fitting of deep neural networks (DNNs). Existing approaches alleviate these issues by adopting a sample…

Meta-learning methods typically learn tasks under the assumption that all tasks are equally important. However, this assumption is often not valid. In real-world applications, tasks can vary both in their importance during different…

As large language models (LLMs) are increasingly deployed in real-world systems, they must support post-hoc removal of specific content to meet privacy and governance requirements. This motivates selective unlearning, which suppresses…

Modern privacy regulations have spurred the evolution of machine unlearning, a technique enabling a trained model to efficiently forget specific training data. In prior unlearning methods, the concept of "data forgetting" is often…

We consider offline Imitation Learning from corrupted demonstrations where a constant fraction of data can be noise or even arbitrary outliers. Classical approaches such as Behavior Cloning assumes that demonstrations are collected by an…

Continual learning aims to enable models to adapt to new datasets without losing performance on previously learned data, often assuming that prior data is no longer available. However, in many practical scenarios, both old and new data are…

Coreset selection aims to identify a small yet highly informative subset of data, thereby enabling more efficient model training while reducing storage overhead. Recently, this capability has been leveraged to tackle the challenges of…

Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning ensures complete data removal equivalent to retraining, it is…

The Right to be Forgotten is a core principle outlined by regulatory frameworks such as the EU's General Data Protection Regulation (GDPR). This principle allows individuals to request that their personal data be deleted from deployed…

Machine unlearning (MU) is gaining increasing attention due to the need to remove or modify predictions made by machine learning (ML) models. While training models have become more efficient and accurate, the importance of unlearning…

In recent years, machine learning neural network has penetrated deeply into people's life. As the price of convenience, people's private information also has the risk of disclosure. The "right to be forgotten" was introduced in a timely…